{"record":{"id":"2ffe662b3ea23ee7","repo":"oobabooga/textgen","slug":"ik-requires-the-ik-llama-cpp-binaries-package-i","errorCode":null,"errorMessage":"--ik requires the ik_llama_cpp_binaries package. Install it with: pip install <ik_llama_cpp_binaries wheel URL>","messagePattern":"--ik requires the ik_llama_cpp_binaries package\\. Install it with: pip install <ik_llama_cpp_binaries wheel URL>","errorType":"exception","errorClass":"ImportError","httpStatus":null,"severity":"error","filePath":"modules/llama_cpp_server.py","lineNumber":423,"sourceCode":"        \"\"\"Find an available port, preferring main port + 5.\"\"\"\n        preferred_port = shared.args.api_port + 5\n        if self._is_port_available(preferred_port):\n            return preferred_port\n\n        # Fall back to OS-assigned random port\n        with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:\n            s.bind(('', 0))\n            return s.getsockname()[1]\n\n    def _start_server(self):\n        \"\"\"Start the llama.cpp server and wait until it's ready.\"\"\"\n        # Determine the server path\n        if self.server_path is None:\n            if shared.args.ik:\n                try:\n                    import ik_llama_cpp_binaries\n                except ImportError:\n                    raise ImportError(\"--ik requires the ik_llama_cpp_binaries package. Install it with: pip install <ik_llama_cpp_binaries wheel URL>\")\n\n                self.server_path = ik_llama_cpp_binaries.get_binary_path()\n            else:\n                import llama_cpp_binaries\n                self.server_path = llama_cpp_binaries.get_binary_path()\n\n        # Build the command\n        cmd = [\n            self.server_path,\n            \"--model\", self.model_path,\n            \"--batch-size\", str(shared.args.batch_size),\n            \"--ubatch-size\", str(shared.args.ubatch_size),\n            \"--port\", str(self.port),\n            \"--no-webui\",\n            \"--flash-attn\", \"on\",\n        ]\n\n        if shared.args.ctx_size < 0:","sourceCodeStart":405,"sourceCodeEnd":441,"githubUrl":"https://github.com/oobabooga/textgen/blob/ed888c71f221df552750e1834b3654abab8ae345/modules/llama_cpp_server.py#L405-L441","documentation":"Error \"--ik requires the ik_llama_cpp_binaries package. Install it with: pip install <ik_llama_cpp_binaries wheel URL>\" thrown in oobabooga/textgen.","triggerScenarios":"Raised at startup/model-load when the --ik flag (ik_llama.cpp backend) is used but the ik_llama_cpp_binaries package is not installed. Install it with: pip install <ik_llama_cpp_binaries wheel URL>.","commonSituations":"See trigger scenarios.","solutions":["Install the ik_llama_cpp_binaries package with: pip install <ik_llama_cpp_binaries wheel URL>.","Remove the --ik flag to use the standard llama.cpp loader instead."],"exampleFix":null,"handlingStrategy":null,"validationCode":null,"typeGuard":null,"tryCatchPattern":null,"preventionTips":[],"tags":[],"backgroundTag":null,"analyzedSha":"ed888c71f221df552750e1834b3654abab8ae345","analyzedAt":"2026-08-15T05:24:21.000Z","schemaVersion":2},"datasetVersion":"2026-08-15T22:17:37.221Z"}